INDEX

Explanations

references to specific types of products or substances, particularly those related to tobacco and marijuana

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¤

-0.07

apro

-0.07

anou

-0.07

imals

-0.07

áº¡n

-0.06

Ã¡ng

-0.06

teness

-0.06

EMU

-0.06

abal

-0.06

spar

-0.06

POSITIVE LOGITS

 tobacco

0.21

 Tobacco

0.19

 cigarette

0.17

 leaf

0.16

 nicotine

0.16

 cigar

0.16

tob

0.16

 Leaf

0.15

 cigarettes

0.15

 cigars

0.14

Activations Density 0.006%